Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AWS cost optimization, monitoring, and operational excellence expert. Use when analyzing AWS bills, estimating costs, setting up CloudWatch alarms, querying logs, auditing CloudTrail activity, or assessing security posture. Essential when user mentions AWS costs, spending, billing,...
.claude/skills/sickn33-aws-cost-operations/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 158% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 200% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-11 | ✓→✗ | ▼ Worse | -4% | 0% |
This skill provides comprehensive guidance for AWS cost optimization, monitoring, observability, and operational excellence with integrated MCP servers.
Always verify AWS facts using MCP tools (mcp__aws-mcp__* or mcp__*awsdocs*__*) before answering. The aws-mcp-setup dependency is auto-loaded — if MCP tools are unavailable, guide the user through that skill's setup flow.
This plugin provides 3 MCP servers:
pricing)Purpose: Pre-deployment cost estimation and optimization
costexp)Purpose: Detailed cost analysis and reporting
cw)Purpose: Metrics, alarms, and logs analysis
> Note: The following servers are available separately via the Full AWS MCP Server (see aws-mcp-setup skill) and are not bundled with this plugin: > - AWS Billing and Cost Management MCP — Real-time billing details > - CloudWatch Application Signals MCP — APM and SLOs > - AWS Managed Prometheus MCP — PromQL queries for containers > - AWS CloudTrail MCP — API activity audit > - AWS Well-Architected Security Assessment MCP — Security posture assessment
Use this skill when:
Always estimate costs before deploying:
Example workflow:
"Estimate the monthly cost of running a Lambda function with
1 million invocations, 512MB memory, 3-second duration in us-east-1"Regular cost reviews:
Cost optimization strategies:
Track spending against budgets:
Implement comprehensive monitoring:
Example alarm scenarios:
Monitor application health:
For containerized workloads:
Audit AWS activity:
Common audit scenarios:
Regular security reviews:
Security assessment areas:
For detailed operational patterns and best practices, refer to the comprehensive reference:
File: references/operations-patterns.md
This reference includes:
File: references/cloudwatch-alarms.md
Common alarm configurations for:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→pass | 5,810 | 3,175 | -45% | 1 | 1 | 0% | 1,046 | 2,458 | +135% | 0 | 0 | — |
case-14 | pass→pass | 7,177 | 4,707 | -34% | 1 | 1 | 0% | 1,382 | 2,652 | +92% | 0 | 0 | — |
case-03 | fail→fail | 18,027 | 27,201 | +51% | 1 | 1 | 0% | 3,645 | 6,475 | +78% | 0 | 0 | — |
case-01 | fail→fail | 16,490 | 6,172 | -63% | 1 | 1 | 0% | 3,590 | 2,344 | -35% | 0 | 0 | — |
case-02 | fail→fail | 20,631 | 4,809 | -77% | 1 | 1 | 0% | 3,692 | 2,065 | -44% | 0 | 0 | — |
case-04 | fail→fail | 12,956 | 10,023 | -23% | 1 | 1 | 0% | 3,075 | 2,329 | -24% | 0 | 0 | — |
case-05 | fail→fail | 11,936 | 13,669 | +15% | 1 | 1 | 0% | 2,713 | 4,748 | +75% | 0 | 0 | — |
case-06 | fail→fail | 14,939 | 12,404 | -17% | 1 | 1 | 0% | 2,611 | 4,036 | +55% | 0 | 0 | — |
case-07 | fail→pass | 11,555 | 5,043 | -56% | 1 | 1 | 0% | 2,064 | 2,880 | +40% | 0 | 0 | — |
case-08 | pass→pass | 9,069 | 2,389 | -74% | 1 | 1 | 0% | 1,573 | 2,312 | +47% | 0 | 0 | — |
case-10 | pass→pass | 12,153 | 6,040 | -50% | 1 | 1 | 0% | 2,357 | 2,990 | +27% | 0 | 0 | — |
case-11 | pass→fail | 12,774 | 4,685 | -63% | 1 | 1 | 0% | 2,167 | 2,073 | -4% | 0 | 0 | — |
case-12 | pass→pass | 6,270 | 4,153 | -34% | 1 | 1 | 0% | 1,048 | 2,568 | +145% | 0 | 0 | — |
case-13 | fail→pass | 5,673 | 6,743 | +19% | 1 | 1 | 0% | 1,186 | 3,064 | +158% | 0 | 0 | — |
case-15 | pass→pass | 8,565 | 4,907 | -43% | 1 | 1 | 0% | 1,498 | 2,807 | +87% | 0 | 0 | — |
case-16 | fail→pass | 6,731 | 6,071 | -10% | 1 | 1 | 0% | 1,069 | 3,202 | +200% | 0 | 0 | — |
case-17 | pass→pass | 13,353 | 13,546 | +1% | 1 | 1 | 0% | 2,637 | 4,323 | +64% | 0 | 0 | — |
case-18 | fail→pass | 7,694 | 3,521 | -54% | 1 | 1 | 0% | 1,261 | 2,505 | +99% | 0 | 0 | — |
case-19 | pass→pass | 10,595 | 7,105 | -33% | 1 | 1 | 0% | 1,870 | 3,259 | +74% | 0 | 0 | — |
case-20 | pass→pass | 8,650 | 8,009 | -7% | 1 | 1 | 0% | 1,508 | 3,145 | +109% | 0 | 0 | — |
case-21 | pass→pass | 13,908 | 10,961 | -21% | 1 | 1 | 0% | 2,717 | 3,799 | +40% | 0 | 0 | — |
case-22 | pass→pass | 12,956 | 11,733 | -9% | 1 | 1 | 0% | 2,617 | 4,305 | +65% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +14 percentage points is the difference between those two pass rates over the 18 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.